Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c3521b4a5d28582a192bf625e3b3d9a7d0a05bfde31d6f83952ad6b205ed0d8
+oid sha256:cee784595b36b7f463340e6a98a1de2cd4f37340449120834fe1f090c35308f3
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdfc0c287cceaa8623057c715583877af1c55841a37a8f0bf8781a14ff1db48
+oid sha256:e1f34668123cf714d4f723abd53b077680c8a2191eafc7b8429d8dd5540bf5f2
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c7805b57b08f6f9a9fa50f5bedc22ad48282cda889c0a72d37b771b9081b04
+oid sha256:274c2461ba45d23ff586a6b66059a6abcee8c69326dcde96eee77251914ccafc
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8912ffac78147b85d155b32cce13a61d79ebe5a45967161ea395b5dca18015a9
+oid sha256:649f870f171779f79fb82050d7a8ec23d27f88fccd7447e4fea42c56756db5a6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f081f3b895ea3d6286bbe2ace8e44e8ca6c644a4af68bfbdb90dc9f5bbdfd372
+oid sha256:c7ae49804d75b275fcaed609a7838b956173bffd19f165bfb614ebfb52041dbf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7743a1f0cc0e52f0f39178cc0fc67d0736e571c6023324f3880d656ee3c25e2e
+oid sha256:093eae11d0f78cbed0c6541a92031fd7215b6a6cbd9b5441592c5ba42ee52ea9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6588581204414368,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.018316695668101474,
+  "best_metric": 0.5693678259849548,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03663339133620295,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 18.706,
       "eval_steps_per_second": 2.34,
       "step": 25
+    },
+    {
+      "epoch": 0.019049363494825534,
+      "grad_norm": 1.6137243509292603,
+      "learning_rate": 5e-05,
+      "loss": 0.7756,
+      "step": 26
+    },
+    {
+      "epoch": 0.01978203132154959,
+      "grad_norm": 1.26747465133667,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6441,
+      "step": 27
+    },
+    {
+      "epoch": 0.02051469914827365,
+      "grad_norm": 1.2265703678131104,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.627,
+      "step": 28
+    },
+    {
+      "epoch": 0.02124736697499771,
+      "grad_norm": 1.0557516813278198,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5974,
+      "step": 29
+    },
+    {
+      "epoch": 0.021980034801721768,
+      "grad_norm": 1.0866754055023193,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6379,
+      "step": 30
+    },
+    {
+      "epoch": 0.022712702628445828,
+      "grad_norm": 1.123220443725586,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5748,
+      "step": 31
+    },
+    {
+      "epoch": 0.023445370455169888,
+      "grad_norm": 1.2740416526794434,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5974,
+      "step": 32
+    },
+    {
+      "epoch": 0.024178038281893945,
+      "grad_norm": 1.1661179065704346,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4786,
+      "step": 33
+    },
+    {
+      "epoch": 0.024910706108618005,
+      "grad_norm": 1.375145673751831,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6214,
+      "step": 34
+    },
+    {
+      "epoch": 0.025643373935342065,
+      "grad_norm": 1.1276419162750244,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5566,
+      "step": 35
+    },
+    {
+      "epoch": 0.026376041762066125,
+      "grad_norm": 1.2904120683670044,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5779,
+      "step": 36
+    },
+    {
+      "epoch": 0.02710870958879018,
+      "grad_norm": 1.4637553691864014,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6633,
+      "step": 37
+    },
+    {
+      "epoch": 0.02784137741551424,
+      "grad_norm": 1.1279934644699097,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7174,
+      "step": 38
+    },
+    {
+      "epoch": 0.0285740452422383,
+      "grad_norm": 0.9128093719482422,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6951,
+      "step": 39
+    },
+    {
+      "epoch": 0.029306713068962358,
+      "grad_norm": 0.9181010723114014,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5927,
+      "step": 40
+    },
+    {
+      "epoch": 0.03003938089568642,
+      "grad_norm": 0.8616317510604858,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5294,
+      "step": 41
+    },
+    {
+      "epoch": 0.03077204872241048,
+      "grad_norm": 0.9883503913879395,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6009,
+      "step": 42
+    },
+    {
+      "epoch": 0.03150471654913454,
+      "grad_norm": 0.9856258034706116,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5573,
+      "step": 43
+    },
+    {
+      "epoch": 0.032237384375858595,
+      "grad_norm": 0.9469846487045288,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4878,
+      "step": 44
+    },
+    {
+      "epoch": 0.03297005220258265,
+      "grad_norm": 0.8723491430282593,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4456,
+      "step": 45
+    },
+    {
+      "epoch": 0.033702720029306715,
+      "grad_norm": 0.9594306349754333,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5013,
+      "step": 46
+    },
+    {
+      "epoch": 0.03443538785603077,
+      "grad_norm": 1.0781900882720947,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5283,
+      "step": 47
+    },
+    {
+      "epoch": 0.03516805568275483,
+      "grad_norm": 1.1100373268127441,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5124,
+      "step": 48
+    },
+    {
+      "epoch": 0.03590072350947889,
+      "grad_norm": 1.2396796941757202,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6077,
+      "step": 49
+    },
+    {
+      "epoch": 0.03663339133620295,
+      "grad_norm": 1.576565146446228,
+      "learning_rate": 0.0,
+      "loss": 0.7111,
+      "step": 50
+    },
+    {
+      "epoch": 0.03663339133620295,
+      "eval_loss": 0.5693678259849548,
+      "eval_runtime": 496.4155,
+      "eval_samples_per_second": 18.523,
+      "eval_steps_per_second": 2.317,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null